Unlock instant, AI-driven research and patent intelligence for your innovation.

Collision Detection Optimization Method Based on Curvature Point Clustering and Decision Tree

A technology of collision detection and decision tree, which is applied in the research fields of computer vision and virtual reality, can solve the problems of complex intersection test, difficult structure, and poor compactness, so as to save redundant calculation, improve model accuracy, and high efficiency Effect

Active Publication Date: 2021-11-19
NANJING UNIV OF INFORMATION SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the four bounding box algorithms, there are various shortcomings such as difficult construction, poor compactness, complex intersection test, and low efficiency.
There have been many studies trying to mix various bounding boxes to complement each other, but the effect is not good

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Collision Detection Optimization Method Based on Curvature Point Clustering and Decision Tree
  • Collision Detection Optimization Method Based on Curvature Point Clustering and Decision Tree
  • Collision Detection Optimization Method Based on Curvature Point Clustering and Decision Tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0048] The specific steps of the blood vessel collision detection optimization method based on curvature point clustering and decision tree in this embodiment are as follows:

[0049] Step 1, selecting hierarchical bounding boxes based on curvature point clustering and geometric features;

[0050] The original intention of using the bounding box is to exclude object pairs that are unlikely to collide. The four common hierarchical bounding box models are spherical bounding box, bounding box along the coordinate axis, direction bounding box and discrete directed polyhedron bounding box. Each has its own advantages and disadvantages. ;Calculate the curvature of the contour points of different types of collision objects, analyze their geometric characteristics, use the K-means clustering algorithm to improve the matching degree of the bounding bo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a collision detection optimization method based on curvature point clustering and decision tree, comprising the following steps: step 1, selecting a hierarchical bounding box based on curvature point clustering and geometric features; step 2, optimizing the hybrid hierarchical tree based on a decision tree model Establish. This method calculates the curvature of the contour points of different types of collision objects, analyzes their geometric characteristics, uses the K-means clustering algorithm to select a suitable bounding box, and improves the matching degree between the bounding box and the collision object; uses the Boosting algorithm to improve the accuracy of the decision tree model, saving The redundant calculation in the original collision detection algorithm is removed, the establishment process of the hybrid hierarchical tree is optimized, and the efficiency of collision detection is improved.

Description

technical field [0001] The invention belongs to the research field of computer vision and virtual reality, in particular to a collision detection optimization method based on curvature point clustering and decision tree. Background technique [0002] The higher the accuracy of the human soft tissue model, the more complex the model and the greater the amount of calculation. Reducing the amount of calculation in the process of model loading and collision detection, and improving the speed of collision detection can effectively improve the real-time performance of the virtual surgery simulation system. At present, the collision detection algorithm of spatial structure mainly includes space division method and hierarchical bounding box method. The former simulates the whole scene through hierarchical subdivision technology, focusing on reducing the object pairs that may collide; the latter constructs a hierarchical bounding box for each object. Scenario simulation, focusing on...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/246G06T7/11G06T7/136G06T7/13G06T7/90G06K9/62G16H50/50
CPCG06T7/0012G06T7/11G06T7/13G06T7/136G06T7/246G06T7/90G16H50/50G06T2207/30004G06T2207/10016G06T2207/20081G06F18/23213G06F18/214
Inventor 张小瑞吴韵清孙伟宋爱国刘佳
Owner NANJING UNIV OF INFORMATION SCI & TECH